mlsanityData to 7 Oct 2026

Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communication

arXiv 2312.01823 ↗First posted 4 Dec 2023cs.CLcited by 78

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Large Language Models (LLMs) have recently made significant strides in complex reasoning tasks through the Chain-of-Thought technique. Despite this progress, their reasoning is often constrained by their intrinsic understanding, lacking external insights. To address this, we propose Exchange-of-Thought (EoT), a novel framework that enables cross-model communication during problem-solving. Drawing inspiration from network topology, EoT integrates four unique communication paradigms: Memory, Report, Relay, and Debate. This paper delves into the communication dynamics and volume associated with each paradigm. To counterbalance the risks of incorrect reasoning chains, we implement a robust confidence evaluation mechanism within these communications. Our experiments across diverse complex reasoning tasks demonstrate that EoT significantly surpasses established baselines, underscoring the value of external insights in enhancing LLM performance. Furthermore, we show that EoT achieves these superior results in a cost-effective manner, marking a promising advancement for efficient and collaborative AI problem-solving.

Key facts. Cited by 78 papers in the map (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 36 of its 70 references that are in the map. First posted on arXiv 4 Dec 2023.

Builds on

36 of 70 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debate23 May
  2. 2023LLaMA: Open and Efficient Foundation Language Models27 Feb
  3. 2022PAL: Program-aided Language Models18 Nov

Other references · 33

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  4. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  5. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  6. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  7. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  8. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  9. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  10. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  11. 2023Efficient Streaming Language Models with Attention Sinkscited by 2,115
  12. 2022LaMDA: Language Models for Dialog Applicationscited by 1,218
21 more
  1. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,199
  2. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,057
  3. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 995
  4. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 965
  5. 2023Extending Context Window of Large Language Models via Positional Interpolationcited by 721
  6. 2023RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedbackcited by 615
  7. 2023Faithful Chain-of-Thought Reasoningcited by 285
  8. 2023Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedbackcited by 202
  9. 2023Augmenting Language Models with Long-Term Memorycited by 186
  10. 2023Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Futurecited by 184
  11. 2023The Capacity for Moral Self-Correction in Large Language Modelscited by 171
  12. 2023Active Prompting with Chain-of-Thought for Large Language Modelscited by 154
  13. 2023Progressive-Hint Prompting Improves Reasoning in Large Language Modelscited by 147
  14. 2023Unified Demonstration Retriever for In-Context Learningcited by 141
  15. 2023Focused Transformer: Contrastive Training for Context Scalingcited by 133
  16. 2023Scaling Laws of RoPE-based Extrapolationcited by 124
  17. 2023Can Large Language Models Really Improve by Self-critiquing Their Own Plans?cited by 107
  18. 2023Finding Support Examples for In-Context Learningcited by 104
  19. 2023GPT-4 Doesn't Know It's Wrong: An Analysis of Iterative Prompting for Reasoning Problemscited by 88
  20. 2023Boosting Language Models Reasoning with Chain-of-Knowledge Promptingcited by 77
  21. 2023MoT: Memory-of-Thought Enables ChatGPT to Self-Improvecited by 37

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 19; 2025: 37; 2026: 22.

78 papers.

Sort:

By area:

  1. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMscited by 424
  2. 2024Scaling Large Language Model-based Multi-Agent Collaborationcited by 235
  3. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 194
  4. 2024Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systemscited by 129
  5. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  6. 2025G-Memory: Tracing Hierarchical Memory for Multi-Agent Systemscited by 112
  7. 2024G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networkscited by 110
  8. 2024CriticBench: Benchmarking LLMs for Critique-Correct Reasoningcited by 88
  9. 2024Language Agents as Optimizable Graphscited by 81
  10. 2025MemEvolve: Meta-Evolution of Agent Memory Systemscited by 81
  11. 2025MasRouter: Learning to Route LLMs for Multi-Agent Systemscited by 80
  12. 2025Assemble Your Crew: Automatic Multi-agent Communication Topology Design via Autoregressive Graph Generationcited by 57
38 more
  1. 2025Voting or Consensus? Decision-Making in Multi-Agent Debatecited by 55
  2. 2025Stop Overvaluing Multi-Agent Debate -- We Must Rethink Evaluation and Embrace Model Heterogeneitycited by 43
  3. 2024MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoningcited by 40
  4. 2024Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraintcited by 39
  5. 2025Removal of Hallucination on Hallucination: Debate-Augmented RAGcited by 29
  6. 2024Provable Scaling Laws for the Test-Time Compute of Large Language Modelscited by 25
  7. 2024AutoPRM: Automating Procedural Supervision for Multi-Step Reasoning via Controllable Question Decompositioncited by 24
  8. 2025Stay Focused: Problem Drift in Multi-Agent Debatecited by 23
  9. 2024Text Generation: A Systematic Literature Review of Tasks, Evaluation, and Challengescited by 18
  10. 2024Measuring Social Norms of Large Language Modelscited by 16
  11. 2025MALLM: Multi-Agent Large Language Models Frameworkcited by 15
  12. 2025Maestro: Learning to Collaborate via Conditional Listwise Policy Optimization for Multi-Agent LLMscited by 14
  13. 2024Synergy-of-Thoughts: Eliciting Efficient Reasoning in Hybrid Language Modelscited by 13
  14. 2026LatentMem: Customizing Latent Memory for Multi-Agent Systemscited by 12
  15. 2024Hint-before-Solving Prompting: Guiding LLMs to Effectively Utilize Encoded Knowledgecited by 10
  16. 2025Instruct-of-Reflection: Enhancing Large Language Models Iterative Reflection Capabilities via Dynamic-Meta Instructioncited by 10
  17. 2025Exploring Advanced LLM Multi-Agent Systems Based on Blackboard Architecturecited by 10
  18. 2026The Five Ws of Multi-Agent Communication: Who Talks to Whom, When, What, and Why -- A Survey from MARL to Emergent Language and LLMscited by 10
  19. 2025MAMM-Refine: A Recipe for Improving Faithfulness in Generation with Multi-Agent Collaborationcited by 9
  20. 2026Adaptive Collaboration with Humans: Metacognitive Policy Optimization for Multi-Agent LLMs with Continual Learningcited by 9
  21. 2025Amplified Vulnerabilities: Structured Jailbreak Attacks on LLM-based Multi-Agent Debatecited by 8
  22. 2025Collective Reasoning Among LLMs: A Framework for Answer Validation Without Ground Truthcited by 7
  23. 2025Long Context Scaling: Divide and Conquer via Multi-Agent Question-driven Collaborationcited by 7
  24. 2024Cooperative Strategic Planning Enhances Reasoning Capabilities in Large Language Modelscited by 6
  25. 2024Enhancing Answer Reliability Through Inter-Model Consensus of Large Language Modelscited by 6
  26. 2025CortexDebate: Debating Sparsely and Equally for Multi-Agent Debatecited by 6
  27. 2024GenoTEX: An LLM Agent Benchmark for Automated Gene Expression Data Analysiscited by 5
  28. 2025Emergent Bias and Fairness in Multi-Agent Decision Systemscited by 5
  29. 2024Automated Collection of Evaluation Dataset for Semantic Search in Low-Resource Domain Languagecited by 4
  30. 2025When and Why Does Multi-Agent Debate Fail and Does It Really Underperform?cited by 4
  31. 2025Perspective Transition of Large Language Models for Solving Subjective Taskscited by 3
  32. 2025Learning Together to Perform Better: Teaching Small-Scale LLMs to Collaborate via Preferential Rationale Tuningcited by 3
  33. 2025Bridging Literature and the Universe Via A Multi-Agent Large Language Model Systemcited by 3
  34. 2026Multi-Agent Debate Strategies: Survey, Taxonomy, and Challengescited by 3
  35. 2024360^circREA: Towards A Reusable Experience Accumulation with 360deg Assessment for Multi-Agent Systemcited by 2
  36. 2025Strategic Planning and Rationalizing on Trees Make LLMs Better Debaterscited by 2
  37. 2025Swarm Intelligence Enhanced Reasoning: A Density-Driven Framework for LLM-Based Multi-Agent Optimizationcited by 2
  38. 2025Explaining Matters: Leveraging Definitions and Semantic Expansion for Sexism Detectioncited by 2

50 most cited of 78 All 78 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Reasoning Relay: Evaluating Stability and Interchangeability of Large Language Models in Mathematical Reasoning
  2. 2025The Price of Thought: A Multilingual Analysis of Reasoning, Performance, and Cost of Negotiation in Large Language Models
  3. 2023Chain-of-Thought Hub: A Continuous Effort to Measure Large Language Models' Reasoning Performance
  4. 2023ChatCoT: Tool-Augmented Chain-of-Thought Reasoning on Chat-based Large Language Models
  5. 2025Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning
  6. 2024Chain-of-Thought in Large Language Models: Decoding, Projection, and Activation
  7. 2025Theorem-of-Thought: A Multi-Agent Framework for Abductive, Deductive, and Inductive Reasoning in Language Models
  8. 2025Advancing Reasoning in Large Language Models: Promising Methods and Approaches